Hugging Face's logo

gowitheflow
/
p9-iter3

Text Classification
Transformers
PyTorch
pixel
Generated from Trainer
Inference Endpoints
Model card Files Community
p9-iter3
File size: 2,144 Bytes 
ed73917
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
 
{
  "best_metric": 0.7974429202242631,
  "best_model_checkpoint": "00-allnli-p9-allnli-p9-allnli-p9-allnli-old-best/checkpoint-2600",
  "epoch": 1.0586319218241043,
  "global_step": 2600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "learning_rate": 3e-05,
      "loss": 0.129,
      "step": 200
    },
    {
      "epoch": 0.16,
      "learning_rate": 2.75e-05,
      "loss": 0.0665,
      "step": 400
    },
    {
      "epoch": 0.24,
      "learning_rate": 2.5e-05,
      "loss": 0.0754,
      "step": 600
    },
    {
      "epoch": 0.33,
      "learning_rate": 2.25e-05,
      "loss": 0.0806,
      "step": 800
    },
    {
      "epoch": 0.41,
      "learning_rate": 1.9999999999999998e-05,
      "loss": 0.0895,
      "step": 1000
    },
    {
      "epoch": 0.49,
      "learning_rate": 1.7500000000000002e-05,
      "loss": 0.0959,
      "step": 1200
    },
    {
      "epoch": 0.57,
      "learning_rate": 1.5e-05,
      "loss": 0.1116,
      "step": 1400
    },
    {
      "epoch": 0.65,
      "learning_rate": 1.25e-05,
      "loss": 0.1274,
      "step": 1600
    },
    {
      "epoch": 0.73,
      "learning_rate": 9.999999999999999e-06,
      "loss": 0.1436,
      "step": 1800
    },
    {
      "epoch": 0.81,
      "learning_rate": 7.5e-06,
      "loss": 0.1621,
      "step": 2000
    },
    {
      "epoch": 0.9,
      "learning_rate": 4.9999999999999996e-06,
      "loss": 0.1891,
      "step": 2200
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.4999999999999998e-06,
      "loss": 0.2067,
      "step": 2400
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0,
      "loss": 0.1854,
      "step": 2600
    },
    {
      "epoch": 1.06,
      "step": 2600,
      "total_flos": 172275249862656.0,
      "train_loss": 0.12790855224315936,
      "train_runtime": 1337.6408,
      "train_samples_per_second": 248.796,
      "train_steps_per_second": 1.944
    }
  ],
  "max_steps": 2600,
  "num_train_epochs": 2,
  "total_flos": 172275249862656.0,
  "trial_name": null,
  "trial_params": null
}